docs/interface/wrappers.md

+# Environment Wrappers
+
+> We provide various environment wrappers to work with both the rail env and the petting zoo interface.
+
+## Background
+
+These wrappers changes certain environment behavior which can help to get better reinforcement learning training.
+
+## Supported Inbuilt Wrappers
+
+We provide 2 sample wrappers for ShortestPathAction wrapper and SkipNoChoice wrapper. The wrappers requires many env properties that are only created on environment reset. Hence before using the wrapper, we must reset the rail env. To use the wrappers, simply pass the resetted rail env. Code samples are shown below for each wrapper.
+
+### ShortestPathAction Wrapper
+
+To use the ShortestPathAction Wrapper, simply wrap the rail env as follows
+
+```python
+rail_env.reset(random_seed=1)
+rail_env = ShortestPathActionWrapper(rail_env)
+```
+
+The shortest path action wrapper maps the existing action space into 3 actions - Shortest Path (`0`), Next Shortest Path (`1`) and Stop (`2`).  Hence, we must ensure that the predicted action should always be one of these (0, 1 and 2) actions. To route all agents in the shortest path, pass `0` as the action.
+
+### SkipNoChoice Wrapper
+
+To use the SkipNoChoiceWrapper, simply wrap the rail env as follows
+
+```python
+rail_env.reset(random_seed=1)
+rail_env = SkipNoChoiceCellsWrapper(rail_env, accumulate_skipped_rewards=False, discounting=0.0)
+```

docs/interface/wrappers.rst

+
+Environment Wrappers
+====================
+
+..
+
+   We provide various environment wrappers to work with both the rail env and the petting zoo interface.
+
+
+Background
+----------
+
+These wrappers changes certain environment behavior which can help to get better reinforcement learning training.
+
+Supported Inbuilt Wrappers
+--------------------------
+
+We provide 2 sample wrappers for ShortestPathAction wrapper and SkipNoChoice wrapper. The wrappers requires many env properties that are only created on environment reset. Hence before using the wrapper, we must reset the rail env. To use the wrappers, simply pass the resetted rail env. Code samples are shown below for each wrapper.
+
+ShortestPathAction Wrapper
+^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+To use the ShortestPathAction Wrapper, simply wrap the rail env as follows
+
+.. code-block:: python
+
+   rail_env.reset(random_seed=1)
+   rail_env = ShortestPathActionWrapper(rail_env)
+
+The shortest path action wrapper maps the existing action space into 3 actions - Shortest Path (\ ``0``\ ), Next Shortest Path (\ ``1``\ ) and Stop (\ ``2``\ ).  Hence, we must ensure that the predicted action should always be one of these (0, 1 and 2) actions. To route all agents in the shortest path, pass ``0`` as the action.
+
+SkipNoChoice Wrapper
+^^^^^^^^^^^^^^^^^^^^
+
+To use the SkipNoChoiceWrapper, simply wrap the rail env as follows
+
+.. code-block:: python
+
+   rail_env.reset(random_seed=1)
+   rail_env = SkipNoChoiceCellsWrapper(rail_env, accumulate_skipped_rewards=False, discounting=0.0)

docs/localevaluation.rst

-================
-Local Evaluation
-================
-
-This document explains you how to locally evaluate your submissions before making 
-an official submission to the competition.
-
-Requirements
-------------
-
-* **flatland-rl** : We expect that you have `flatland-rl` installed by following the instructions in  :doc:`installation`.
-
-* **redis** : Additionally you will also need to have  `redis installed <https://redis.io/topics/quickstart>`_ and **should have it running in the background.**
-
-Test Data
----------
-
-* **test env data** : You can `download and untar the test-env-data <https://www.aicrowd.com/challenges/flatland-challenge/dataset_files>`, at a location of your choice, lets say `/path/to/test-env-data/`. After untarring the folder, the folder structure should look something like:
-
-
-.. code-block:: console
-
-    .
-    └── test-env-data
-        ├── Test_0
-        │   ├── Level_0.pkl
-        │   └── Level_1.pkl
-        ├── Test_1
-        │   ├── Level_0.pkl
-        │   └── Level_1.pkl
-        ├..................
-        ├..................
-        ├── Test_8
-        │   ├── Level_0.pkl
-        │   └── Level_1.pkl
-        └── Test_9
-            ├── Level_0.pkl
-            └── Level_1.pkl
-
-Evaluation Service
-------------------
-
-* **start evaluation service** : Then you can start the evaluator by running : 
-
-.. code-block:: console
-
-    flatland-evaluator --tests /path/to/test-env-data/
-
-RemoteClient
-------------
-
-* **run client** : Some `sample submission code can be found in the starter-kit <https://github.com/AIcrowd/flatland-challenge-starter-kit/>`_, but before you can run your code locally using `FlatlandRemoteClient`, you will have to set the `AICROWD_TESTS_FOLDER` environment variable to the location where you previous untarred the folder with `the test-env-data`:
-
-
-.. code-block:: console
-
-    export AICROWD_TESTS_FOLDER="/path/to/test-env-data/"
-
-    # or on Windows :
-    # 
-    # set AICROWD_TESTS_FOLDER "\path\to\test-env-data\"
-
-    # and then finally run your code
-    python run.py
-

docs/specifications/core.md

-# Core Specifications
-## Environment Class Overview
+## Core Specifications
+
+### Environment Class Overview
 
 The Environment class contains all necessary functions for the interactions between the agents and the environment. The base Environment class is derived from rllib.env.MultiAgentEnv (https://github.com/ray-project/ray).
 
@@ -12,7 +13,7 @@ class Environment:
 
     Agents are identified by agent ids (handles).
     Examples:
-        >>> obs = env.reset()
+        >>> obs, info = env.reset()
         >>> print(obs)
         {
             "train_0": [2.4, 1.6],

docs/specifications/intro.md

+## Intro
+
+In a human-readable language, specifications provide
+- code base overview (hand-drawn concept)
+- key concepts (generators, envs) and how are they linked
+- link relevant code base
+
+![Overview](img/UML_flatland.png)
+`Diagram Source <https://confluence.sbb.ch/x/pQfsSw>`_

docs/intro_observation_actions.rst → docs/specifications/intro_observation_actions.rst

-=============================
+
 Observation and Action Spaces
-=============================
+----------------------------
 This is an introduction to the three standard observations and the action space of **Flatland**.
 
 Action Space
-============
+^^^^^^^^^^^^
 Flatland is a railway simulation. Thus the actions of an agent are strongly limited to the railway network. This means that in many cases not all actions are valid.
 The possible actions of an agent are
 
@@ -15,7 +15,7 @@ The possible actions of an agent are
 - ``4`` **Stop**: This action causes the agent to stop.
 
 Observation Spaces
-==================
+^^^^^^^^^^^^^^^^^^
 In the **Flatland** environment we have included three basic observations to get started. The figure below illustrates the observation range of the different basic observation: ``Global``, ``Local Grid`` and ``Local Tree``.
 
 .. image:: https://i.imgur.com/oo8EIYv.png
@@ -24,7 +24,7 @@ In the **Flatland** environment we have included three basic observations to get
 
    
 Global Observation
-------------------
+~~~~~~~~~~~~~~~~~~
 Gives a global observation of the entire rail environment.
 
 The observation is composed of the following elements:
@@ -37,7 +37,7 @@ We encourage you to enhance this observation with any layer you think might help
 It would also be possible to construct a global observation for a super agent that controls all agents at once.
 
 Local Grid Observation
-----------------------
+~~~~~~~~~~~~~~~~~~~~~~
 Gives a local observation of the rail environment around the agent.
 The observation is composed of the following elements:
 
@@ -50,7 +50,7 @@ Be aware that this observation **does not** contain any clues about target locat
 We encourage you to come up with creative ways to overcome this problem. In the tree observation below we introduce the concept of distance maps.
 
 Tree Observation
-----------------
+~~~~~~~~~~~~~~~~
 The tree observation is built by exploiting the graph structure of the railway network. The observation is generated by spanning a **4 branched tree** from the current position of the agent. Each branch follows the allowed transitions (backward branch only allowed at dead-ends) until a cell with multiple allowed transitions is reached. Here the information gathered along the branch is stored as a node in the tree.
 The figure below illustrates how the tree observation is built:
 
@@ -73,7 +73,7 @@ The right side of the figure shows the resulting tree of the railway network on
     
     
 Node Information
-----------------
+~~~~~~~~~~~~~~~~
 Each node is filled with information gathered along the path to the node. Currently each node contains 9 features:
 
 - 1: if own target lies on the explored branch the current distance from the agent in number of cells is stored.

docs/specifications/rendering.md

-# Rendering Specifications
+## Rendering Specifications
 
-## Scope
+### Scope
 This doc specifies the software to meet the requirements in the Visualization requirements doc.
 
-## References
+### References
 - [Visualization Requirements](visualization)
 - [Core Spec](./core)
 
-## Interfaces
-### Interface with Environment Component
+### Interfaces
+#### Interface with Environment Component
 
 - Environment produces the Env Snapshot data structure (TBD)
 - Renderer reads the Env Snapshot
@@ -28,9 +28,9 @@ This doc specifies the software to meet the requirements in the Visualization re
     - Or, render frames without blocking environment
         - Render frames in separate process / thread
 
-#### Environment Snapshot
+##### Environment Snapshot
 
-### Data Structure
+#### Data Structure
 
 A definitions of the data structure is to be defined in Core requirements or Interfaces doc.
 
@@ -50,7 +50,7 @@ Top-level dictionary
         - Tree-based observation
             - TBD
 
-### Existing Tools / Libraries
+#### Existing Tools / Libraries
 1. Pygame
     1. Very easy to use. Like dead simple to add sprites etc. [Link](https://studywolf.wordpress.com/2015/03/06/arm-visualization-with pygame/)
     2. No inbuilt support for threads/processes. Does get faster if using pypy/pysco.
@@ -58,18 +58,18 @@ Top-level dictionary
     1. Somewhat simple, a little more verbose to use the different modules.
     2. Multi-threaded via QThread! Yay! (Doesn’t block main thread that does the real work), [Link](https://nikolak.com/pyqt-threading-tutorial/)
 
-#### How to structure the code
+##### How to structure the code
 
 1. Define draw functions/classes for each primitive
     1. Primitives: Agents (Trains), Railroad, Grass, Houses etc.
 2. Background. Initialize the background before starting the episode.
     1. Static objects in the scenes, directly draw those primitives once and cache.
 
-#### Proposed Interfaces
+##### Proposed Interfaces
 To-be-filled
 
-### Technical Graphics Considerations
+#### Technical Graphics Considerations
 
-#### Overlay dynamic primitives over the background at each time step.
+##### Overlay dynamic primitives over the background at each time step.
 
 No point trying to figure out changes. Need to explicitly draw every primitive anyways (that’s how these renders work).

docs/specifications/visualization.md

-# Visualization
+## Visualization
 
 ![logo](https://drive.google.com/uc?export=view&id=1rstqMPJXFJd9iD46z1A5Rus-W0Ww6O8i)
 
 
-# Introduction & Scope
+### Introduction & Scope
 
 Broad requirements for human-viewable display of a single Flatland Environment.
 
 
-## Context
+#### Context
 
 Shows this software component in relation to some of the other components.  We name the component the "Renderer".  Multiple agents interact with a single Environment.  A renderer interacts with the environment, and displays on screen, and/or into movie or image files.
 
@@ -20,10 +20,10 @@ Shows this software component in relation to some of the other components.  We n
 ![drawing](https://docs.google.com/a/google.com/drawings/d/12345/export/png)
 
 
-# Requirements
+### Requirements
 
 
-## Primary Requirements
+#### Primary Requirements
 
 
 
@@ -39,7 +39,7 @@ Shows this software component in relation to some of the other components.  We n
     7. Should not drive the "main loop" of Inference or training 
 
 
-## Secondary / Optional Requirements 
+#### Secondary / Optional Requirements 
 
 
 
@@ -68,7 +68,7 @@ Shows this software component in relation to some of the other components.  We n
     15. Browser
 
 
-## Performance Metrics
+#### Performance Metrics
 
 Here are some performance metrics which the Renderer should meet.
 
@@ -78,7 +78,7 @@ Here are some performance metrics which the Renderer should meet.
    <td>
    </td>
    <td><p style="text-align: right">
-# Per second</p>
+### Per second</p>
 
    </td>
    <td><p style="text-align: right">
@@ -144,15 +144,15 @@ Prototype time (ms)</p>
 
 
 
-## Example Visualization
+#### Example Visualization
 
 
-# Reference Documents
+### Reference Documents
 
 Link to this doc: https://docs.google.com/document/d/1Y4Mw0Q6r8PEOvuOZMbxQX-pV2QKDuwbZJBvn18mo9UU/edit#
 
 
-## Core Specification
+#### Core Specification
 
 This specifies the system containing the environment and agents - this will be able to run independently of the renderer.
 
@@ -161,24 +161,24 @@ This specifies the system containing the environment and agents - this will be a
 The data structure which the renderer needs to read initially resides here.
 
 
-## Visualization Specification
+#### Visualization Specification
 
 This will specify the software which will meet the requirements documented here.
 
 [https://docs.google.com/document/d/1XYOe_aUIpl1h_RdHnreACvevwNHAZWT0XHDL0HsfzRY/edit#](https://docs.google.com/document/d/1XYOe_aUIpl1h_RdHnreACvevwNHAZWT0XHDL0HsfzRY/edit#)
 
 
-## Interface Specification
+#### Interface Specification
 
 This will specify the interfaces through which the different components communicate
 
 
-# Non-requirements - to be deleted below here.
+### Non-requirements - to be deleted below here.
 
 The below has been copied into the spec doc.    Comments may be lost.  I'm only preserving it to save the comments for a few days - they don't cut & paste into the other doc!
 
 
-## Interface with Environment Component
+#### Interface with Environment Component
 
 
 
@@ -201,7 +201,7 @@ The below has been copied into the spec doc.    Comments may be lost.  I'm only
         *   Render frames in separate process / thread
 
 
-#### Environment Snapshot
+###### Environment Snapshot
 
 **Data Structure**
 
@@ -227,7 +227,7 @@ Top-level dictionary
             *   TBD
 
 
-## Investigation into Existing Tools / Libraries
+#### Investigation into Existing Tools / Libraries
 
 
 
@@ -252,9 +252,9 @@ Top-level dictionary
 To-be-filled
 
 
-## Technical Graphics Considerations
+#### Technical Graphics Considerations
 
 
-#### Overlay dynamic primitives over the background at each time step.
+###### Overlay dynamic primitives over the background at each time step.
 
 No point trying to figure out changes. Need to explicitly draw every primitive anyways (that's how these renders work).

docs/specifications_index.rst

-Flatland Specs
-==============
-
-.. toctree::
-   :maxdepth: 2
-
-   specifications/specifications.md
-   specifications/core.md
-   specifications/railway.md
-   specifications/rendering.md
-   specifications/specifications.md
-   specifications/visualization.md

docs/gettingstarted.rst → docs/tutorials/01_gettingstarted.rst

-===============
-Getting Started
-===============
+Getting Started Tutorial
+========================
 
 Overview
 --------
@@ -16,14 +15,14 @@ To use flatland in a project:
     import flatland
 
 
-Part 1 : Basic Usage
---------------------
-
+Simple Example 1 : Basic Usage
+------------------------------
 The basic usage of RailEnv environments consists in creating a RailEnv object
 endowed with a rail generator, that generates new rail networks on each reset,
 and an observation generator object, that is supplied with environment-specific
 information at each time step and provides a suitable observation vector to the
-agents.
+agents. After the RailEnv environment is created, one need to call reset() on the
+environment in order to fully initialize the environment
 
 The simplest rail generators are envs.rail_generators.rail_from_manual_specifications_generator
 and envs.rail_generators.random_rail_generator.
@@ -45,6 +44,7 @@ For example,
                   rail_generator=rail_from_manual_specifications_generator(specs),
                   number_of_agents=1,
                   obs_builder_object=TreeObsForRailEnv(max_depth=2))
+    env.reset()
 
 Alternatively, a random environment can be generated (optionally specifying
 weights for each cell type to increase or decrease their proportion in the
@@ -73,6 +73,7 @@ generated rail networks).
                             ),
                   number_of_agents=3,
                   obs_builder_object=TreeObsForRailEnv(max_depth=2))
+    env.reset()
 
 Environments can be rendered using the utils.rendertools utilities, for example:
 
@@ -108,19 +109,17 @@ following code. Also, tree observation data is displayed by RenderTool by defaul
     for i in range(env.get_num_agents()):
         env.obs_builder.util_print_obs_subtree(
                 tree=obs[i],
-                num_features_per_node=5
                 )
 
 The complete code for this part of the Getting Started guide can be found in
 
 * `examples/simple_example_1.py <https://gitlab.aicrowd.com/flatland/flatland/blob/master/examples/simple_example_1.py>`_
 * `examples/simple_example_2.py <https://gitlab.aicrowd.com/flatland/flatland/blob/master/examples/simple_example_2.py>`_
-* `examples/simple_example_3.py <https://gitlab.aicrowd.com/flatland/flatland/blob/master/examples/simple_example_3.py>`_
-
 
 
 Part 2 : Training a Simple an Agent on Flatland
------------------------------------------------
+---------------------------------------------------------
+
 This is a brief tutorial on how to train an agent on Flatland.
 Here we use a simple random agent to illustrate the process on how to interact with the environment.
 The corresponding code can be found in examples/training_example.py and in the baselines repository
@@ -146,8 +145,9 @@ Next we configure the difficulty of our task by modifying the complex_rail_gener
                                         nr_extra=10,
                                         min_dist=10,
                                         max_dist=99999,
-                                        seed=0),
+                                        seed=1),
                     number_of_agents=5)
+    env.reset()
 
 The difficulty of a railway network depends on the dimensions (`width` x `height`) and the number of agents in the network.
 By varying the number of start and goal connections (nr_start_goal) and the number of extra railway elements added (nr_extra)
@@ -161,13 +161,13 @@ Once we are set with the environment we can load our preferred agent from either
 
 .. code-block:: python
 
-    agent = RandomAgent(env.action_space, env.observation_space)
+    agent = RandomAgent(state_size, action_size)
 
 We start every trial by resetting the environment
 
 .. code-block:: python
 
-    obs = env.reset()
+    obs, info = env.reset()
 
 Which provides the initial observation for all agents (obs = array of all observations).
 In order for the environment to step forward in time we need a dictionar of actions for all active agents.
@@ -187,77 +187,4 @@ This dictionary is then passed to the environment which checks the validity of a
 The environment returns an array of new observations, reward dictionary for all agents as well as a flag for which agents are done.
 This information can be used to update the policy of your agent and if done['__all__'] == True the episode terminates.
 
-Part 3 : Customizing Observations and Level Generators
-------------------------------------------------------
-
-Example code for generating custom observations given a RailEnv and to generate
-random rail maps are available in examples/custom_observation_example.py and
-examples/custom_railmap_example.py .
-
-Custom observations can be produced by deriving a new object from the
-core.env_observation_builder.ObservationBuilder base class, for example as follows:
-
-.. code-block:: python
-
-    class CustomObs(ObservationBuilder):
-        def __init__(self):
-            self.observation_space = [5]
-
-        def reset(self):
-            return
-
-        def get(self, handle):
-            observation = handle*np.ones((5,))
-            return observation
-
-It is important that an observation_space is defined with a list of dimensions
-of the returned observation tensors. get() returns the observation for each agent,
-of handle 'handle'.
-
-A RailEnv environment can then be created as usual:
-
-.. code-block:: python
-
-    env = RailEnv(width=7,
-                  height=7,
-                  rail_generator=random_rail_generator(),
-                  number_of_agents=3,
-                  obs_builder_object=CustomObs())
-
-As for generating custom rail maps, the RailEnv class accepts a rail_generator
-argument that must be a function with arguments `width`, `height`, `num_agents`,
-and `num_resets=0`, and that has to return a GridTransitionMap object (the rail map),
-and three lists of tuples containing the (row,column) coordinates of each of
-num_agent agents, their initial orientation **(0=North, 1=East, 2=South, 3=West)**,
-and the position of their targets.
-
-For example, the following custom rail map generator returns an empty map of
-size (height, width), with no agents (regardless of num_agents):
-
-.. code-block:: python
-
-    def custom_rail_generator():
-        def generator(width, height, num_agents=0, num_resets=0):
-            rail_trans = RailEnvTransitions()
-            grid_map = GridTransitionMap(width=width, height=height, transitions=rail_trans)
-            rail_array = grid_map.grid
-            rail_array.fill(0)
-
-            agents_positions = []
-            agents_direction = []
-            agents_target = []
-
-            return grid_map, agents_positions, agents_direction, agents_target
-        return generator
-
-It is worth to note that helpful utilities to manage RailEnv environments and their
-related data structures are available in 'envs.env_utils'. In particular,
-envs.env_utils.get_rnd_agents_pos_tgt_dir_on_rail is fairly handy to fill in
-random (but consistent) agents along with their targets and initial directions,
-given a rail map (GridTransitionMap object) and the desired number of agents:
-
-.. code-block:: python
-
-    agents_position, agents_direction, agents_target = get_rnd_agents_pos_tgt_dir_on_rail(
-        rail_map,
-        num_agents)
+The full source code of this example can be found in `examples/training_example.py <https://gitlab.aicrowd.com/flatland/flatland/blob/master/examples/training_example.py>`_.

docs/intro_observationbuilder.rst → docs/tutorials/02_observationbuilder.rst

-==============================================================
-Getting Started with custom observations and custom predictors
-==============================================================
+Custom observations and custom predictors Tutorial
+==================================================
 
 Overview
 --------
@@ -19,7 +18,7 @@ base class and must implement two methods, :code:`reset(self)` and :code:`get(se
 
 .. _`flatland.core.env_observation_builder.ObservationBuilder` : https://gitlab.aicrowd.com/flatland/flatland/blob/master/flatland/core/env_observation_builder.py#L13
 
-Below is a simple example that returns observation vectors of size :code:`observation_space = 5` featuring only the ID (handle) of the agent whose
+Below is a simple example that returns observation vectors of size 5 featuring only the ID (handle) of the agent whose
 observation vector is being computed:
 
 .. code-block:: python
@@ -29,14 +28,12 @@ observation vector is being computed:
         Simplest observation builder. The object returns observation vectors with 5 identical components,
         all equal to the ID of the respective agent.
         """
-        def __init__(self):
-            self.observation_space = [5]
 
         def reset(self):
             return
 
         def get(self, handle):
-            observation = handle * np.ones((self.observation_space[0],))
+            observation = handle * np.ones(5)
             return observation
 
 We can pass an instance of our custom observation builder :code:`SimpleObs` to the :code:`RailEnv` creator as follows:
@@ -48,6 +45,7 @@ We can pass an instance of our custom observation builder :code:`SimpleObs` to t
                   rail_generator=random_rail_generator(),
                   number_of_agents=3,
                   obs_builder_object=SimpleObs())
+    env.reset()
 
 Anytime :code:`env.reset()` or :code:`env.step()` is called, the observation builder will return the custom observation of all agents initialized in the env.
 In the next example we highlight how to derive from existing observation builders and how to access internal variables of **Flatland**.
@@ -86,7 +84,6 @@ Note that this simple strategy fails when multiple agents are present, as each a
             super().__init__(max_depth=0)
             # We set max_depth=0 in because we only need to look at the current
             # position of the agent to decide what direction is shortest.
-            self.observation_space = [3]
 
         def reset(self):
             # Recompute the distance map, if the environment has changed.
@@ -122,9 +119,10 @@ Note that this simple strategy fails when multiple agents are present, as each a
     env = RailEnv(width=7,
                   height=7,
                   rail_generator=complex_rail_generator(nr_start_goal=10, nr_extra=1, \
-                    min_dist=8, max_dist=99999, seed=0),
+                    min_dist=8, max_dist=99999, seed=1),
                   number_of_agents=2,
                   obs_builder_object=SingleAgentNavigationObs())
+    env.reset()
 
     obs, all_rewards, done, _ = env.step({0: 0, 1: 1})
     for i in range(env.get_num_agents()):
@@ -140,6 +138,7 @@ navigation to target, and shows the path taken as an animation.
                   rail_generator=random_rail_generator(),
                   number_of_agents=1,
                   obs_builder_object=SingleAgentNavigationObs())
+    env.reset()
 
     obs, all_rewards, done, _ = env.step({0: 0})
 
@@ -190,7 +189,6 @@ In contrast to the previous examples we also implement the :code:`def get_many(s
 
         def __init__(self, predictor):
             super().__init__(max_depth=0)
-            self.observation_space = [10]
             self.predictor = predictor
 
         def reset(self):
@@ -272,11 +270,12 @@ We can then use this new observation builder and the renderer to visualize the o
     # Initiate Environment
     env = RailEnv(width=10,
                   height=10,
-                  rail_generator=complex_rail_generator(nr_start_goal=5, nr_extra=1, min_dist=8, max_dist=99999, seed=0),
+                  rail_generator=complex_rail_generator(nr_start_goal=5, nr_extra=1, min_dist=8, max_dist=99999, seed=1),
                   number_of_agents=3,
                   obs_builder_object=CustomObsBuilder)
+    env.reset()
 
-    obs = env.reset()
+    obs, info = env.reset()
     env_renderer = RenderTool(env, gl="PILSVG")
 
     # We render the initial step and show the obsered cells as colored boxes

docs/tutorials/03_rail_and_schedule_generator.md

+# Level Generation Tutorial
+
+We are currently working on different new level generators and you can expect that the levels in the submission testing will not all come from just one but rather different level generators to be sure that the controllers can handle any railway specific challenge.
+
+Let's have a look at the `sparse_rail_generator`.
+
+## Sparse Rail Generator
+![Example_Sparse](https://i.imgur.com/DP8sIyx.png)
+
+The idea behind the sparse rail generator is to mimic classic railway structures where dense nodes (cities) are sparsely connected to each other and where you have to manage traffic flow between the nodes efficiently.
+The cities in this level generator are much simplified in comparison to real city networks but it mimics parts of the problems faced in daily operations of any railway company.
+
+There are a few parameters you can tune to build your own map and test different complexity levels of the levels.
+**Warning** some combinations of parameters do not go well together and will lead to infeasible level generation.
+In the worst case, the level generator currently issues a warning when it cannot build the environment according to the parameters provided.
+This will lead to a crash of the whole env.
+We are currently working on improvements here and are **happy for any suggestions from your side**.
+
+To build an environment you instantiate a `RailEnv` as follows:
+
+```python
+ Initialize the generator
+rail_generator=sparse_rail_generator(
+    num_cities=10,  # Number of cities in map
+    num_intersections=10,  # Number of interesections in map
+    num_trainstations=50,  # Number of possible start/targets on map
+    min_node_dist=6,  # Minimal distance of nodes
+    node_radius=3,  # Proximity of stations to city center
+    num_neighb=3,  # Number of connections to other cities
+    seed=5,  # Random seed
+    grid_mode=False  # Ordered distribution of nodes
+)
+
+ Build the environment
+env = RailEnv(
+    width=50,
+    height=50,
+    rail_generator=rail_generator
+    schedule_generator=sparse_schedule_generator(),
+    number_of_agents=10,
+    obs_builder_object=TreeObsForRailEnv(max_depth=3,predictor=shortest_path_predictor)
+)
+ Call reset on the environment
+env.reset()
+```
+
+You can see that you now need both a `rail_generator` and a `schedule_generator` to generate a level. These need to work nicely together. The `rail_generator` will only generate the railway infrastructure and provide hints to the `schedule_generator` about where to place agents. The `schedule_generator` will then generate a schedule, meaning it places agents at different train stations and gives them tasks by providing individual targets.
+
+You can tune the following parameters in the `sparse_rail_generator`:
+
+- `num_cities` is the number of cities on a map. Cities are the only nodes that can host start and end points for agent tasks (Train stations). Here you have to be carefull that the number is not too high as all the cities have to fit on the map. When `grid_mode=False` you have to be carefull when chosing `min_node_dist` because leves will fails if not all cities (and intersections) can be placed with at least `min_node_dist` between them.
+- `num_intersections` is the number of nodes that don't hold any trainstations. They are also the first priority that a city connects to. We use these to allow for sparse connections between cities.
+- `num_trainstations` defines the *Total* number of trainstations in the network. This also sets the max number of allowed agents in the environment. This is also a delicate parameter as there is only a limitid amount of space available around nodes and thus if the number is too high the level generation will fail. *Important*: Only the number of agents provided to the environment will actually produce active train stations. The others will just be present as dead-ends (See figures below).
+- `min_node_dist` is only used if `grid_mode=False` and represents the minimal distance between two nodes.
+- `node_radius` defines the extent of a city. Each trainstation is placed at a distance to the closes city node that is smaller or equal to this number.
+- `num_neighb`defines the number of neighbouring nodes that connect to each other. Thus this changes the connectivity and thus the amount of alternative routes in the network.
+- `grid_mode` True -> Nodes evenly distriubted in env, False-> Random distribution of nodes
+- `enhance_intersection`: True -> Extra rail elements added at intersections
+- `seed` is used to initialize the random generator
+
+
+If you run into any bugs with sets of parameters please let us know.
+
+Here is a network with `grid_mode=False` and the parameters from above.
+
+![sparse_random](https://i.imgur.com/Xg7nifF.png)
+
+and here with `grid_mode=True`
+
+![sparse_ordered](https://i.imgur.com/jyA7Pt4.png)
+
+## Example code
+
+To see all the changes in action you can just run the `flatland_example_2_0.py` file in the examples folder. The file can be found [here](https://gitlab.aicrowd.com/flatland/flatland/blob/master/examples/flatland_2_0_example.py).

docs/tutorials/04_stochasticity.md

+# Stochasticity Tutorial
+
+Another area where we improved **Flat**land 2.0 are stochastic events added during the episodes.
+This is very common for railway networks where the initial plan usually needs to be rescheduled during operations as minor events such as delayed departure from trainstations, malfunctions on trains or infrastructure or just the weather lead to delayed trains.
+
+We implemted a poisson process to simulate delays by stopping agents at random times for random durations. The parameters necessary for the stochastic events can be provided when creating the environment.
+
+```python
+# Use a the malfunction generator to break agents from time to time
+
+stochastic_data = {
+    'prop_malfunction': 0.5,  # Percentage of defective agents
+    'malfunction_rate': 30,  # Rate of malfunction occurence
+    'min_duration': 3,  # Minimal duration of malfunction
+    'max_duration': 10  # Max duration of malfunction
+}
+```
+
+The parameters are as follows:
+
+- `prop_malfunction` is the proportion of agents that can malfunction. `1.0` means that each agent can break.
+- `malfunction_rate` is the mean rate of the poisson process in number of environment steps.
+- `min_duration` and `max_duration` set the range of malfunction durations. They are sampled uniformly
+
+You can introduce stochasticity by simply creating the env as follows:
+
+```python
+env = RailEnv(
+    ...
+    stochastic_data=stochastic_data,  # Malfunction data generator
+    ...
+)
+```
+In your controller, you can check whether an agent is malfunctioning:
+```python
+obs, rew, done, info = env.step(actions)
+...
+action_dict = dict()
+for a in range(env.get_num_agents()):
+    if info['malfunction'][a] == 0:
+        action_dict.update({a: ...})
+
+# Custom observation builder
+tree_observation = TreeObsForRailEnv(max_depth=2, predictor=ShortestPathPredictorForRailEnv())
+
+# Different agent types (trains) with different speeds.
+speed_ration_map = {1.: 0.25,  # Fast passenger train
+                    1. / 2.: 0.25,  # Fast freight train
+                    1. / 3.: 0.25,  # Slow commuter train
+                    1. / 4.: 0.25}  # Slow freight train
+
+env = RailEnv(width=50,
+              height=50,
+              rail_generator=sparse_rail_generator(num_cities=20,  # Number of cities in map (where train stations are)
+                                                   num_intersections=5,  # Number of intersections (no start / target)
+                                                   num_trainstations=15,  # Number of possible start/targets on map
+                                                   min_node_dist=3,  # Minimal distance of nodes
+                                                   node_radius=2,  # Proximity of stations to city center
+                                                   num_neighb=4,  # Number of connections to other cities/intersections
+                                                   seed=15,  # Random seed
+                                                   grid_mode=True,
+                                                   enhance_intersection=True
+                                                   ),
+              schedule_generator=sparse_schedule_generator(speed_ration_map),
+              number_of_agents=10,
+              stochastic_data=stochastic_data,  # Malfunction data generator
+              obs_builder_object=tree_observation)
+env.reset()
+```
+
+You will quickly realize that this will lead to unforeseen difficulties which means that **your controller** needs to observe the environment at all times to be able to react to the stochastic events.
+
+## Example code
+
+To see all the changes in action you can just run the `flatland_example_2_0.py` file in the examples folder. The file can be found [here](https://gitlab.aicrowd.com/flatland/flatland/blob/master/examples/flatland_2_0_example.py).

docs/specifications/specifications.md → docs/tutorials/05_multispeed.md

-Flatland Specs
-==========================
+# Different speed profiles Tutorial
 
-What are **Flatland** specs about?
----------------------------------
-In a humand-readable language, they provide
-* code base overview (hand-drawn concept)
-* key concepts (generators, envs) and how are they linked
-* link relevant code base
+One of the main contributions to the complexity of railway network operations stems from the fact that all trains travel at different speeds while sharing a very limited railway network.
+In **Flat**land 2.0 this feature will be enabled as well and will lead to much more complex configurations. Here we count on your support if you find bugs or improvements  :).
 
-## Overview
-![UML_flatland.png](img/UML_flatland.png)
-[Diagram Source](https://confluence.sbb.ch/x/pQfsSw)
+The different speed profiles can be generated using the `schedule_generator`, where you can actually chose as many different speeds as you like.
+Keep in mind that the *fastest speed* is 1 and all slower speeds must be between 1 and 0.
+For the submission scoring you can assume that there will be no more than 5 speed profiles.
+
+
+
+Later versions of **Flat**land might have varying speeds during episodes. Therefore, we return the agent speeds.
+Notice that we do not guarantee that the speed will be computed at each step, but if not costly we will return it at each step.
+In your controller, you can get the agents' speed from the `info` returned by `step`:
+```python
+obs, rew, done, info = env.step(actions)
+...
+for a in range(env.get_num_agents()):
+    speed = info['speed'][a]
+```
+
+## Actions and observation with different speed levels
+
+Because the different speeds are implemented as fractions the agents ability to perform actions has been updated.
+We **do not allow actions to change within the cell **.
+This means that each agent can only chose an action to be taken when entering a cell.
+This action is then executed when a step to the next cell is valid. For example
+
+- Agent enters switch and choses to deviate left. Agent fractional speed is 1/4 and thus the agent will take 4 time steps to complete its journey through the cell. On the 4th time step the agent will leave the cell deviating left as chosen at the entry of the cell.
+    - All actions chosen by the agent during its travels within a cell are ignored
+    - Agents can make observations at any time step. Make sure to discard observations without any information. See this [example](https://gitlab.aicrowd.com/flatland/baselines/blob/master/torch_training/training_navigation.py) for a simple implementation.
+- The environment checks if agent is allowed to move to next cell only at the time of the switch to the next cell
 
+In your controller, you can check whether an agent requires an action by checking `info`:
+```python
+obs, rew, done, info = env.step(actions)
+...
+action_dict = dict()
+for a in range(env.get_num_agents()):
+    if info['action_required'][a] and info['malfunction'][a] == 0:
+        action_dict.update({a: ...})
 
+```
+Notice that `info['action_required'][a]` does not mean that the action will have an effect:
+if the next cell is blocked or the agent breaks down, the action cannot be performed and an action will be required again in the next step.
 
 ## Rail Generators and Schedule Generators
 The separation between rail generator and schedule generator reflects the organisational separation in the railway domain
@@ -21,26 +51,31 @@ The separation between rail generator and schedule generator reflects the organi
 Usually, there is a third organisation, which ensures discrimination-free access to the infrastructure for concurrent requests for the infrastructure in a **schedule planning phase**.
 However, in the **Flat**land challenge, we focus on the re-scheduling problem during live operations.
 
-Technically, 
-``` 
+Technically,
+```python
 RailGeneratorProduct = Tuple[GridTransitionMap, Optional[Any]]
 RailGenerator = Callable[[int, int, int, int], RailGeneratorProduct]
 
 AgentPosition = Tuple[int, int]
-ScheduleGeneratorProduct = Tuple[List[AgentPosition], List[AgentPosition], List[AgentPosition], List[float]]
-ScheduleGenerator = Callable[[GridTransitionMap, int, Optional[Any]], ScheduleGeneratorProduct]
+Schedule = collections.namedtuple('Schedule',   'agent_positions '
+                                                'agent_directions '
+                                                'agent_targets '
+                                                'agent_speeds '
+                                                'agent_malfunction_rates '
+                                                'max_episode_steps')
+ScheduleGenerator = Callable[[GridTransitionMap, int, Optional[Any], Optional[int]], Schedule]
 ```
 
 We can then produce `RailGenerator`s by currying:
-```
+```python
 def sparse_rail_generator(num_cities=5, num_intersections=4, num_trainstations=2, min_node_dist=20, node_radius=2,
-                          num_neighb=3, grid_mode=False, enhance_intersection=False, seed=0):
+                          num_neighb=3, grid_mode=False, enhance_intersection=False, seed=1):
 
     def generator(width, height, num_agents, num_resets=0):
-    
+
         # generate the grid and (optionally) some hints for the schedule_generator
         ...
-         
+
         return grid_map, {'agents_hints': {
             'num_agents': num_agents,
             'agent_start_targets_nodes': agent_start_targets_nodes,
@@ -50,7 +85,7 @@ def sparse_rail_generator(num_cities=5, num_intersections=4, num_trainstations=2
     return generator
 ```
 And, similarly, `ScheduleGenerator`s:
-```
+```python
 def sparse_schedule_generator(speed_ratio_map: Mapping[float, float] = None) -> ScheduleGenerator:
     def generator(rail: GridTransitionMap, num_agents: int, hints: Any = None):
         # place agents:
@@ -59,7 +94,7 @@ def sparse_schedule_generator(speed_ratio_map: Mapping[float, float] = None) ->
         # - (initial) speed
         # - malfunction
         ...
-                
+
         return agents_position, agents_direction, agents_target, speeds, agents_malfunction
 
     return generator
@@ -69,7 +104,7 @@ For instance, the way the `sparse_rail_generator` generates the grid, it already
 Hence, `rail_generator` and `schedule_generator` have to match if `schedule_generator` presupposes some specific `agents_hints`.
 
 The environment's `reset` takes care of applying the two generators:
-```
+```python
     def __init__(self,
             ...
              rail_generator: RailGenerator = random_rail_generator(),
@@ -78,8 +113,8 @@ The environment's `reset` takes care of applying the two generators:
              ):
         self.rail_generator: RailGenerator = rail_generator
         self.schedule_generator: ScheduleGenerator = schedule_generator
-        
-    def reset(self, regen_rail=True, replace_agents=True):
+
+    def reset(self, regenerate_rail=True, regenerate_schedule=True):
         rail, optionals = self.rail_generator(self.width, self.height, self.get_num_agents(), self.num_resets)
 
         ...
@@ -89,249 +124,10 @@ The environment's `reset` takes care of applying the two generators:
             if optionals and 'agents_hints' in optionals:
                 agents_hints = optionals['agents_hints']
             self.agents_static = EnvAgentStatic.from_lists(
-                *self.schedule_generator(self.rail, self.get_num_agents(), hints=agents_hints))
-```
-
-
-## RailEnv Speeds
-One of the main contributions to the complexity of railway network operations stems from the fact that all trains travel at different speeds while sharing a very limited railway network. 
-
-The different speed profiles can be generated using the `schedule_generator`, where you can actually chose as many different speeds as you like. 
-Keep in mind that the *fastest speed* is 1 and all slower speeds must be between 1 and 0. 
-For the submission scoring you can assume that there will be no more than 5 speed profiles.
-
-
-Currently (as of **Flat**land 2.0), an agent keeps its speed over the whole episode. 
-
-Because the different speeds are implemented as fractions the agents ability to perform actions has been updated. 
-We **do not allow actions to change within the cell **. 
-This means that each agent can only chose an action to be taken when entering a cell (ie. positional fraction is 0). 
-There is some real railway specific considerations such as reserved blocks that are similar to this behavior. 
-But more importantly we disabled this to simplify the use of machine learning algorithms with the environment. 
-If we allow stop actions in the middle of cells. then the controller needs to make much more observations and not only at cell changes. 
-(Not set in stone and could be updated if the need arises).
-
-The chosen action is then executed when a step to the next cell is valid. For example
-
-- Agent enters switch and choses to deviate left. Agent fractional speed is 1/4 and thus the agent will take 4 time steps to complete its journey through the cell. On the 4th time step the agent will leave the cell deviating left as chosen at the entry of the cell.
-    - All actions chosen by the agent during its travels within a cell are ignored
-    - Agents can make observations at any time step. Make sure to discard observations without any information. See this [example](https://gitlab.aicrowd.com/flatland/baselines/blob/master/torch_training/training_navigation.py) for a simple implementation.
-- The environment checks if agent is allowed to move to next cell only at the time of the switch to the next cell
-
-In your controller, you can check whether an agent requires an action by checking `info`: 
-```
-obs, rew, done, info = env.step(actions) 
-...
-action_dict = dict()
-for a in range(env.get_num_agents()):
-    if info['action_required'][a]:
-        action_dict.update({a: ...})
-
-```
-Notice that `info['action_required'][a]` 
-* if the agent breaks down (see stochasticity below) on entering the cell (no distance elpased in the cell), an action required as long as the agent is broken down;
-when it gets back to work, the action chosen just before will be taken and executed at the end of the cell; you may check whether the agent
-gets healthy again in the next step by checking `info['malfunction'][a] == 1`.
-* when the agent has spent enough time in the cell, the next cell may not be free and the agent has to wait. 
-
-
-Since later versions of **Flat**land might have varying speeds during episodes. 
-Therefore, we return the agents' speed - in your controller, you can get the agents' speed from the `info` returned by `step`: 
-```
-obs, rew, done, info = env.step(actions) 
-...
-for a in range(env.get_num_agents()):
-    speed = info['speed'][a]
-```
-Notice that we do not guarantee that the speed will be computed at each step, but if not costly we will return it at each step.
-
-
-
-
-
-
-
-
-
-## RailEnv Malfunctioning / Stochasticity
-
-Stochastic events may happen during the episodes. 
-This is very common for railway networks where the initial plan usually needs to be rescheduled during operations as minor events such as delayed departure from trainstations, malfunctions on trains or infrastructure or just the weather lead to delayed trains.
-
-We implemted a poisson process to simulate delays by stopping agents at random times for random durations. The parameters necessary for the stochastic events can be provided when creating the environment.
-
-```
-# Use a the malfunction generator to break agents from time to time
-
-stochastic_data = {
-    'prop_malfunction': 0.5,  # Percentage of defective agents
-    'malfunction_rate': 30,  # Rate of malfunction occurence
-    'min_duration': 3,  # Minimal duration of malfunction
-    'max_duration': 10  # Max duration of malfunction
-}
-```
-
-The parameters are as follows:
-
-- `prop_malfunction` is the proportion of agents that can malfunction. `1.0` means that each agent can break.
-- `malfunction_rate` is the mean rate of the poisson process in number of environment steps.
-- `min_duration` and `max_duration` set the range of malfunction durations. They are sampled uniformly
-
-You can introduce stochasticity by simply creating the env as follows:
-
-```
-env = RailEnv(
-    ...
-    stochastic_data=stochastic_data,  # Malfunction data generator
-    ...    
-)
-```
-In your controller, you can check whether an agent is malfunctioning: 
-```
-obs, rew, done, info = env.step(actions) 
-...
-action_dict = dict()
-for a in range(env.get_num_agents()):
-    if info['malfunction'][a] == 0:
-        action_dict.update({a: ...})
-
-# Custom observation builder
-tree_observation = TreeObsForRailEnv(max_depth=2, predictor=ShortestPathPredictorForRailEnv())
-
-# Different agent types (trains) with different speeds.
-speed_ration_map = {1.: 0.25,  # Fast passenger train
-                    1. / 2.: 0.25,  # Fast freight train
-                    1. / 3.: 0.25,  # Slow commuter train
-                    1. / 4.: 0.25}  # Slow freight train
-
-env = RailEnv(width=50,
-              height=50,
-              rail_generator=sparse_rail_generator(num_cities=20,  # Number of cities in map (where train stations are)
-                                                   num_intersections=5,  # Number of intersections (no start / target)
-                                                   num_trainstations=15,  # Number of possible start/targets on map
-                                                   min_node_dist=3,  # Minimal distance of nodes
-                                                   node_radius=2,  # Proximity of stations to city center
-                                                   num_neighb=4,  # Number of connections to other cities/intersections
-                                                   seed=15,  # Random seed
-                                                   grid_mode=True,
-                                                   enhance_intersection=True
-                                                   ),
-              schedule_generator=sparse_schedule_generator(speed_ration_map),
-              number_of_agents=10,
-              stochastic_data=stochastic_data,  # Malfunction data generator
-              obs_builder_object=tree_observation)
-```
-
-
-## Observation Builders
-Every `RailEnv` has an `obs_builder`. The `obs_builder` has full access to the `RailEnv`. 
-The `obs_builder` is called in the `step()` function to produce the observations.
-
-```
-env = RailEnv(
-    ...
-    obs_builder_object=TreeObsForRailEnv(
-        max_depth=2,
-       predictor=ShortestPathPredictorForRailEnv(max_depth=10)
-    ),
-    ...                   
-)
+                self.schedule_generator(self.rail, self.get_num_agents(), hints=agents_hints))
 ```
 
-The two principal observation builders provided are global and tree.
-
-### Global Observation Builder
-`GlobalObsForRailEnv` gives a global observation of the entire rail environment.
-* transition map array with dimensions (env.height, env.width, 16),
-          assuming 16 bits encoding of transitions.
-
-* Two 2D arrays (map_height, map_width, 2) containing respectively the position of the given agent
-         target and the positions of the other agents targets.
-
-* A 3D array (map_height, map_width, 4) wtih
-            - first channel containing the agents position and direction
-            - second channel containing the other agents positions and diretions
-            - third channel containing agent malfunctions
-            - fourth channel containing agent fractional speeds
-            
-### Tree Observation Builder
-`TreeObsForRailEnv` computes the current observation for each agent.
-
-The observation vector is composed of 4 sequential parts, corresponding to data from the up to 4 possible
-movements in a `RailEnv` (up to because only a subset of possible transitions are allowed in RailEnv).
-The possible movements are sorted relative to the current orientation of the agent, rather than NESW as for
-the transitions. The order is:
-
-    [data from 'left'] + [data from 'forward'] + [data from 'right'] + [data from 'back']
-
-Each branch data is organized as:
-
-    [root node information] +
-    [recursive branch data from 'left'] +
-    [... from 'forward'] +
-    [... from 'right] +
-    [... from 'back']
-
-Each node information is composed of 9 features:
-
-1. if own target lies on the explored branch the current distance from the agent in number of cells is stored.
-
-2. if another agents target is detected the distance in number of cells from the agents current location
-    is stored
-
-3. if another agent is detected the distance in number of cells from current agent position is stored.
-
-4. possible conflict detected
-    tot_dist = Other agent predicts to pass along this cell at the same time as the agent, we store the
-     distance in number of cells from current agent position
-
-    0 = No other agent reserve the same cell at similar time
 
-5. if an not usable switch (for agent) is detected we store the distance.
+## Example code
 
-6. This feature stores the distance in number of cells to the next branching  (current node)
-
-7. minimum distance from node to the agent's target given the direction of the agent if this path is chosen
-
-8. agent in the same direction
-    n = number of agents present same direction
-        (possible future use: number of other agents in the same direction in this branch)
-    0 = no agent present same direction
-
-9. agent in the opposite direction
-    n = number of agents present other direction than myself (so conflict)
-        (possible future use: number of other agents in other direction in this branch, ie. number of conflicts)
-    0 = no agent present other direction than myself
-
-10. malfunctioning/blokcing agents
-    n = number of time steps the oberved agent remains blocked
-
-11. slowest observed speed of an agent in same direction
-    1 if no agent is observed
-
-    min_fractional speed otherwise
-
-Missing/padding nodes are filled in with -inf (truncated).
-Missing values in present node are filled in with +inf (truncated).
-
-
-In case of the root node, the values are [0, 0, 0, 0, distance from agent to target, own malfunction, own speed]
-In case the target node is reached, the values are [0, 0, 0, 0, 0].
-
-
-## Predictors
-Predictors make predictions on future agents' moves based on the current state of the environment.
-They are decoupled from observation builders in order to be encapsulate the functionality and to make it re-usable.
-
-For instance, `TreeObsForRailEnv` optionally uses the predicted the predicted trajectories while exploring
-the branches of an agent's future moves to detect future conflicts.
-
-The general call structure is as follows:
-```
-RailEnv.step() 
-               -> ObservationBuilder.get_many() 
-                                                ->  self.predictor.get()
-                                                    self.get()
-                                                    self.get()
-                                                    ...
-```
+To see all the changes in action you can just run the `flatland_example_2_0.py` file in the examples folder. The file can be found [here](https://gitlab.aicrowd.com/flatland/flatland/blob/master/examples/flatland_2_0_example.py).

docs/tutorials/06_round_2_starter_help.md

+# How to get started in Round 2
+
+- [Environment Changes](#environment-changes)
+- [Level generation](#level-generation)
+- [Observations](#observations)
+- [Predictions](#predictions)
+
+## Environment Changes
+There have been some major changes in how agents are being handled in the environment in this Flatland update.
+### Agents
+Agents are no more permant entities in the environment. Now agents will be removed from the environment as soon as they finsish their task. To keep interactions with the environment as simple as possible we do not modify the dimensions of the observation vectors nor the number of agents. Agents that have finished do not require any special treatment from the controller. Any action provided to these agents is simply ignored, just like before.
+
+Start positions of agents are *not unique* anymore. This means that many agents can start from the same position on the railway grid. It is important to keep in mind that whatever agent moves first will block the rest of the agents from moving into the same cell. Thus, the controller can already decide the ordering of the agents from the first step.
+
+## Level Generation
+The levels are now generated using the `sparse_rail_generator` and the `sparse_schedule_generator`
+### Rail Generation
+The rail generation is done in a sequence of steps:
+1. A number of city centers are placed in a a grid of size `(height, width)`
+2. Each city is connected to two neighbouring cities
+3. Internal parallel tracks are generated in each city
+
+
+### Schedule Generation
+The `sparse_schedule_generator` produces tasks for the agents by selecting a starting city and a target city. The agent is then placed on an even track number on the starting city and faced such that a path exists to the target city. The task for the agent is to reach the target position as fast as possible.
+
+In the future we will update how these schedules are generated to allow for more complex tasks
+
+## Observations
+Observations have been updated to reflect the novel features and behaviors of Flatland. Have a look at [observation](https://gitlab.aicrowd.com/flatland/flatland/blob/master/flatland/envs/observations.py) or the documentation for more details on the observations.
+
+## Predicitons
\ No newline at end of file